Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/explore-explicit-write-confirmation.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
'@fission-ai/openspec': patch
---

explore: require explicit, scope-bound confirmation before the skill uses any command or tool that can create, edit, move, or delete a file. The explore skill's guardrails let "if the user asks" cover answers to its own clarifying questions, so an agent could treat a design discussion as a go-ahead and start creating schemas or editing `openspec/config.yaml` uninvited. The skill and the `/opsx:explore` command now instruct the agent to name the proposed artifacts or files, ask a direct yes/no question, and wait for confirmation in a separate message before writing. Read-only commands and tools remain available without confirmation, and expanding the confirmed scope requires another confirmation.
5 changes: 5 additions & 0 deletions .changeset/plain-ascii-explore-diagrams.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
'@fission-ai/openspec': patch
---

Draw explore-mode diagrams with plain ASCII. The worked examples in the explore skill and `/opsx:explore` command used Unicode box-drawing, arrow, and marker glyphs, whose display width varies across terminals, fonts, and locales. Agents copied the style, causing padded boxes and aligned tables to drift.
115 changes: 59 additions & 56 deletions skills/openspec-explore/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ metadata:

Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.

**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing. For a new change, scaffold it first as described below.
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, investigate the codebase, and run read-only commands or tools without confirmation, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create or update OpenSpec change artifacts (proposals, designs, specs) within a confirmed scope—that's capturing thinking, not implementing. Answering design or clarifying questions is never consent to write. Before the first write-capable action, name the artifacts or files you would change and what you would do, ask a direct yes/no question, and wait for the user's confirmation in a separate message. Confirmation covers only the scope you described; ask again before expanding it. For a new change, scaffold it first as described below.

**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.

Expand Down Expand Up @@ -54,22 +54,25 @@ Depending on what the user brings, you might:

**Visualize**
```
┌─────────────────────────────────────────┐
Use ASCII diagrams liberally
├─────────────────────────────────────────┤
┌────────┐ ┌────────┐
│ State │────────▶│ State │
│ A B
└────────┘ └────────┘
System diagrams, state machines,
data flows, architecture sketches,
dependency graphs, comparison tables
└─────────────────────────────────────────┘
+------------------------------------------+
| Use ASCII diagrams liberally |
+------------------------------------------+
| |
| [State A] -------> [State B] |
| | |
| v |
| [State C] |
| |
| System diagrams, state machines, |
| data flows, architecture sketches, |
| dependency graphs, comparison tables |
| |
+------------------------------------------+
```

**Draw with plain ASCII only** — borders `+` `-` `|`, arrows `-->` `<--` `^` `v`, markers `*` `x`.
Unicode diagram glyphs can render at different widths across terminals, fonts, and locales, so padded boxes and aligned tables can drift. Keep every diagram character ASCII.

**Surface risks and unknowns**
- Identify what could go wrong
- Find gaps in understanding
Expand Down Expand Up @@ -170,17 +173,17 @@ User: I'm thinking about adding real-time collaboration
You: Real-time collab is a big space. Let me think about this...

COLLABORATION SPECTRUM
════════════════════════════════════════════
============================================

Awareness Coordination Sync
┌────────┐ ┌────────┐ ┌────────┐
Presence Cursors CRDT
"3 Multi Conflict
online" select free
└────────┘ └────────┘ └────────┘
| | |
v v v
+--------+ +--------+ +--------+
|Presence| |Cursors | | CRDT |
| "3 | | Multi | |Conflict|
|online" | | select | | free |
+--------+ +--------+ +--------+
| | |
trivial moderate complex

Where's your head at?
Expand All @@ -192,27 +195,27 @@ User: The auth system is a mess

You: [reads codebase]

┌─────────────────────────────────────────────┐
CURRENT AUTH FLOW
└─────────────────────────────────────────────┘
┌─────────────┼─────────────┐
┌─────────┐ ┌─────────┐ ┌─────────┐
Google │ │ GitHub │ │ Email
OAuth │ │ OAuth │ │ Magic
└────┬────┘ └────┬────┘ └────┬────┘
└─────────────┼─────────────┘
┌───────────┐
Session
└─────┬─────┘
┌───────────┐
Perms
└───────────┘
+---------------------------------------------+
| CURRENT AUTH FLOW |
+---------------------------------------------+
|
+-------------+-------------+
v v v
+---------+ +---------+ +---------+
| Google | | GitHub | | Email |
| OAuth | | OAuth | | Magic |
+----+----+ +----+----+ +----+----+
| | |
+-------------+-------------+
v
+-----------+
| Session |
+-----+-----+
|
v
+-----------+
| Perms |
+-----------+

I see three tangles. Which one's burning?
```
Expand Down Expand Up @@ -244,19 +247,19 @@ User: A CLI tool that tracks local dev environments

You: That changes everything.

┌─────────────────────────────────────────────────┐
CLI TOOL DATA STORAGE
└─────────────────────────────────────────────────┘
+-------------------------------------------------+
| CLI TOOL DATA STORAGE |
+-------------------------------------------------+

Key constraints:
No daemon running
Must work offline
Single user
- No daemon running
- Must work offline
- Single user

SQLite Postgres
Deployment embedded needs server
Offline yes no ✗
Single file yes no ✗
Deployment embedded needs server
Offline yes no
Single file yes no

SQLite. Not even close.

Expand Down Expand Up @@ -296,11 +299,11 @@ But this summary is optional. Sometimes the thinking IS the value.

## Guardrails

- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
- **Don't implement** - Never write code or implement features. Workflow configuration counts too: creating or editing schemas, templates, or `openspec/config.yaml` is a change, not thinking. Creating or updating OpenSpec change artifacts within the confirmed scope is fine, writing anything else is not.
- **Don't fake understanding** - If something is unclear, dig deeper
- **Don't rush** - Discovery is thinking time, not task time
- **Don't force structure** - Let patterns emerge naturally
- **Don't auto-capture** - Offer to save insights, don't just do it
- **Don't auto-capture** - Offer to save insights, don't just do it. Read-only commands and tools need no confirmation. Before the first write-capable action—including `openspec new change` or another command that writes files—name the artifacts or files and proposed changes, ask a direct yes/no question, and wait for explicit confirmation in a separate user message. That confirmation covers only the described scope; ask again before expanding it. Answers to design or clarifying questions are never consent to write.
- **Don't manually scaffold changes** - Never create a new change directory under `openspec/changes/` by hand. Always use `openspec new change "<name>"` (with `--store <id>` when applicable) so required metadata such as `.openspec.yaml` is created before writing artifacts.
- **Do visualize** - A good diagram is worth many paragraphs
- **Do explore the codebase** - Ground discussions in reality
Expand Down
Loading
Loading